Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 5275
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical impact or damage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hit" and its synonyms related to being affected or impacted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aspiration
    -0.69
    rouse
    -0.64
     intentions
    -0.64
    ourage
    -0.61
     pedigree
    -0.61
     superiority
    -0.60
     Directions
    -0.59
    acity
    -0.58
    emp
    -0.56
     disguise
    -0.56
    POSITIVE LOGITS
     aback
    1.01
    quished
    0.87
    livious
    0.85
    Ń·
    0.76
    by
    0.74
     severely
    0.74
    ousel
    0.73
     Hispan
    0.72
     badly
    0.71
    vik
    0.71
    Activations Density 0.153%

    No Known Activations